| 1. |
- Bulten, W, et al.
(författare)
-
Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challenge
- 2022
-
Ingår i: Nature medicine. - : Springer Science and Business Media LLC. - 1546-170X .- 1078-8956. ; 28:1, s. 154-
-
Tidskriftsartikel (refereegranskat)abstract
- Artificial intelligence (AI) has shown promise for diagnosing prostate cancer in biopsies. However, results have been limited to individual studies, lacking validation in multinational settings. Competitions have been shown to be accelerators for medical imaging innovations, but their impact is hindered by lack of reproducibility and independent validation. With this in mind, we organized the PANDA challenge—the largest histopathology competition to date, joined by 1,290 developers—to catalyze development of reproducible AI algorithms for Gleason grading using 10,616 digitized prostate biopsies. We validated that a diverse set of submitted algorithms reached pathologist-level performance on independent cross-continental cohorts, fully blinded to the algorithm developers. On United States and European external validation sets, the algorithms achieved agreements of 0.862 (quadratically weighted κ, 95% confidence interval (CI), 0.840–0.884) and 0.868 (95% CI, 0.835–0.900) with expert uropathologists. Successful generalization across different patient populations, laboratories and reference standards, achieved by a variety of algorithmic approaches, warrants evaluating AI-based Gleason grading in prospective clinical trials.
|
|
| 2. |
- Egevad, L, et al.
(författare)
-
Identification of areas of grading difficulties in prostate cancer and comparison with artificial intelligence assisted grading
- 2020
-
Ingår i: Virchows Archiv : an international journal of pathology. - : Springer Science and Business Media LLC. - 1432-2307. ; 477:6, s. 777-786
-
Tidskriftsartikel (refereegranskat)abstract
- The International Society of Urological Pathology (ISUP) hosts a reference image database supervised by experts with the purpose of establishing an international standard in prostate cancer grading. Here, we aimed to identify areas of grading difficulties and compare the results with those obtained from an artificial intelligence system trained in grading. In a series of 87 needle biopsies of cancers selected to include problematic cases, experts failed to reach a 2/3 consensus in 41.4% (36/87). Among consensus and non-consensus cases, the weighted kappa was 0.77 (range 0.68–0.84) and 0.50 (range 0.40–0.57), respectively. Among the non-consensus cases, four main causes of disagreement were identified: the distinction between Gleason score 3 + 3 with tangential cutting artifacts vs. Gleason score 3 + 4 with poorly formed or fused glands (13 cases), Gleason score 3 + 4 vs. 4 + 3 (7 cases), Gleason score 4 + 3 vs. 4 + 4 (8 cases) and the identification of a small component of Gleason pattern 5 (6 cases). The AI system obtained a weighted kappa value of 0.53 among the non-consensus cases, placing it as the observer with the sixth best reproducibility out of a total of 24. AI may serve as a decision support and decrease inter-observer variability by its ability to make consistent decisions. The grading of these cancer patterns that best predicts outcome and guides treatment warrants further clinical and genetic studies. Results of such investigations should be used to improve calibration of AI systems.
|
|
| 3. |
|
|
| 4. |
|
|
| 5. |
|
|
| 6. |
|
|
| 7. |
|
|
| 8. |
|
|
| 9. |
|
|
| 10. |
|
|
| 11. |
|
|
| 12. |
- Juhlin, CC, et al.
(författare)
-
Perithyroidal Salivary Gland Acinic Cell Carcinoma: Morphological and Molecular Attributes of a Unique Lesion
- 2021
-
Ingår i: Head and neck pathology. - : Springer Science and Business Media LLC. - 1936-0568. ; 15:2, s. 628-637
-
Tidskriftsartikel (refereegranskat)abstract
- Rarely, salivary gland tumors such as mucoepidermoid carcinoma, mammary analogue secretory carcinoma and mucinous carcinoma arise as primary tumors from ectopic or metaplastic salivary gland tissue adjacent to or within the thyroid gland. We report for the first time a case of primary salivary acinic cell carcinoma (AcCC) adjacent to the thyroid gland in a 71-year-old female patient with Crohns disease and a previous history of malignant melanoma. Following the development of a nodule adjacent to the left thyroid lobe, a fine-needle aspiration biopsy was reported as consistent with a follicular lesion of undetermined significance (Bethesda III). A left-sided hemithyroidectomy was performed. A circumscribed lesion measuring 33 mm was noted adjacent to the thyroid and trapping parathyroid, it was composed of solid nests and glands with microcystic and follicular patterns. The tumor was negative for thyroid, parathyroid and paraganglioma markers, but positive for pan-cytokeratins, CK7, CD10, CD117, androgen receptor and HNF-beta. A metastasis of a thyroid-like renal cell carcinoma was suspected but ruled out, and the patient had no evident lesions on extensive radiology of the urogenital, pulmonary and GI tracts. Based on the morphology, a diagnosis of AcCC was suggested, and confirmed with DOG1 and PAS-diastase staining. Molecular analyses pinpointed a constitutional ASXL1 variant of uncertain significance, but no fusion events. The patient had no radiological or clinical evidence of parotid, submandibular or sublingual tumors postoperatively, and the excised lesion was therefore assumed to be a primary tumor. We here detail the morphological and immunophenotypic profile of this previously undescribed perithyroidal tumor.
|
|
| 13. |
|
|
| 14. |
|
|
| 15. |
|
|
| 16. |
- Strom, P, et al.
(författare)
-
Prognostic value of perineural invasion in prostate needle biopsies: a population-based study of patients treated by radical prostatectomy
- 2020
-
Ingår i: Journal of clinical pathology. - : BMJ. - 1472-4146 .- 0021-9746. ; 73:10, s. 630-635
-
Tidskriftsartikel (refereegranskat)abstract
- Despite being one of the major pathways for the spread of malignant tumours, perineural invasion (PNI) has not conclusively been shown to have an independent prognostic value for prostate cancer. Prostatic biopsy constitutes the major pathology workload in prostate cancer and is the foundation for primary treatment decisions and for this reason we aimed to estimate the prognostic value of PNI in biopsies.MethodsWe followed 918 men who underwent radical prostatectomy (RP) from the prospective and population based STHLM3 study until biochemical recurrence with a median follow-up of 4.1 years. To strengthen the evidence, we combined the estimates from the largest studies targeting the prognostic value of PNI in the biopsy. We also estimated the OR of advanced stage as radical prostatectomy for PNI positive and negative men.ResultsThe estimated prognostic value based on our data suggested an approximately 50% increased risk of biochemical recurrence if PNI was present in the biopsy (p=0.06). Even though not statistically significant on the 5% level, this estimate is consistent with similar studies, and by combining the estimates there is in fact strong evidence in support of an independent prognostic value of PNI in the biopsy (p<0.0001). There was also an independent increased risk of advanced stage at RP for positive men (OR 1.85, p=0.005).ConclusionsThe evidence supporting a clinically relevant and independent prognostic value of PNI is strong enough to be considered for pathology reporting guidelines.
|
|
| 17. |
- Akgul, M, et al.
(författare)
-
Diagnostic approach in TFE3-rearranged renal cell carcinoma: a multi-institutional international survey
- 2021
-
Ingår i: Journal of clinical pathology. - : BMJ. - 1472-4146 .- 0021-9746. ; 74:5, s. 291-299
-
Tidskriftsartikel (refereegranskat)abstract
- Transcription factor E3-rearranged renal cell carcinoma (TFE3-RCC) has heterogenous morphologic and immunohistochemical (IHC) features.131 pathologists with genitourinary expertise were invited in an online survey containing 23 questions assessing their experience on TFE3-RCC diagnostic work-up.Fifty (38%) participants completed the survey. 46 of 50 participants reported multiple patterns, most commonly papillary pattern (almost always 9/46, 19.5%; frequently 29/46, 63%). Large epithelioid cells with abundant cytoplasm were the most encountered cytologic feature, with either clear (almost always 10/50, 20%; frequently 34/50, 68%) or eosinophilic (almost always 4/49, 8%; frequently 28/49, 57%) cytology. Strong (3+) or diffuse (>75% of tumour cells) nuclear TFE3 IHC expression was considered diagnostic by 13/46 (28%) and 12/47 (26%) participants, respectively. Main TFE3 IHC issues were the low specificity (16/42, 38%), unreliable staining performance (15/42, 36%) and background staining (12/42, 29%). Most preferred IHC assays other than TFE3, cathepsin K and pancytokeratin were melan A (44/50, 88%), HMB45 (43/50, 86%), carbonic anhydrase IX (41/50, 82%) and CK7 (32/50, 64%). Cut-off for positive TFE3 fluorescent in situ hybridisation (FISH) was preferably 10% (9/50, 18%), although significant variation in cut-off values was present. 23/48 (48%) participants required TFE3 FISH testing to confirm TFE3-RCC regardless of the histomorphologic and IHC assessment. 28/50 (56%) participants would request additional molecular studies other than FISH assay in selected cases, whereas 3/50 participants use additional molecular cases in all cases when TFE3-RCC is in the differential.Optimal diagnostic approach on TFE3-RCC is impacted by IHC and/or FISH assay preferences as well as their conflicting interpretation methods.
|
|
| 18. |
- Beijert, Irene J., et al.
(författare)
-
International Opinions on Grading of Urothelial Carcinoma : A Survey Among European Association of Urology and International Society of Urological Pathology Members
- 2023
-
Ingår i: European Urology Open Science. - 2666-1691. ; 52, s. 154-165
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Grade of non–muscle-invasive bladder cancer (NMIBC) is an important prognostic factor for progression. Currently, two World Health Organization (WHO) classification systems (WHO1973, categories: grade 1–3, and WHO2004 categories: papillary urothelial neoplasm of low malignant potential [PUNLMP], low-grade [LG], high-grade [HG] carcinoma) are used. Objective: To ask the European Association of Urology (EAU) and International Society of Urological Pathology (ISUP) members regarding their current practice and preferences of grading systems. Design, setting, and participants: A web-based, anonymous questionnaire with ten questions on grading of NMIBC was created. The members of EAU and ISUP were invited to complete an online survey by the end of 2021. Thirteen experts had previously answered the same questions. Outcome measurements and statistical analysis: The submitted answers from 214 ISUP members, 191 EAU members, and 13 experts were analyzed. Results and limitations: Currently, 53% use only the WHO2004 system and 40% use both systems. According to most respondents, PUNLMP is a rare diagnosis with management similar to Ta-LG carcinoma. The majority (72%) would consider reverting back to WHO1973 if grading criteria were more detailed. Separate reporting of WHO1973-G3 within WHO2004-HG would influence clinical decisions for Ta and/or T1 tumors according the majority (55%). Most respondents preferred a two-tier (41%) or a three-tier (41%) grading system. The current WHO2004 grading system is supported by a minority (20%), whereas nearly half (48%) supported a hybrid three- or four-tier grading system composed of both WHO1973 and WHO2004. The survey results of the experts were comparable with ISUP and EAU respondents. Conclusions: Both the WHO1973 and the WHO2004 grading system are still widely used. Even though opinions on the future of bladder cancer grading were strongly divided, there was limited support for WHO1973 and WHO2004 in their current formats, while the hybrid (three-tier) grading system with LG, HG-G2, and HG-G3 as categories could be considered the most promising alternative. Patient summary: Grading of non–muscle-invasive bladder cancer (NMIBC) is a matter of ongoing debate and lacks international consensus. We surveyed urologists and pathologists of European Association of Urology and International Society of Urological Pathology on their preferences regarding NMIBC grading to generate a multidisciplinary dialogue. Both the “old” World Health Organization (WHO) 1973 and the “new” WHO2004 grading schemes are still used widely. However, continuation of both the WHO1973 and the WHO2004 system showed limited support, while a hybrid grading system composed of both the WHO1973 and the WHO2004 classification system may be considered a promising alternative.
|
|
| 19. |
|
|
| 20. |
|
|
| 21. |
- Egevad, L, et al.
(författare)
-
Benign mimics of prostate cancer
- 2021
-
Ingår i: Pathology. - : Elsevier BV. - 1465-3931 .- 0031-3025. ; 53:1, s. 26-35
-
Tidskriftsartikel (refereegranskat)
|
|
| 22. |
- Egevad, L, et al.
(författare)
-
Recent advances in urological pathology
- 2021
-
Ingår i: Pathology. - : Elsevier BV. - 1465-3931 .- 0031-3025. ; 53:1, s. 1-2
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)
|
|
| 23. |
|
|
| 24. |
|
|
| 25. |
- Flach, RN, et al.
(författare)
-
Use of the ISUP e-learning module improves interrater reliability in prostate cancer grading
- 2024
-
Ingår i: Journal of clinical pathology. - : BMJ. - 1472-4146 .- 0021-9746. ; 77:1, s. 22-26
-
Tidskriftsartikel (refereegranskat)abstract
- Prostate cancer (PCa) grading is an important prognostic parameter, but is subject to considerable observer variation. Previous studies have shown that interobserver variability decreases after participants were trained using an e-learning module. However, since the publication of these studies, grading of PCa has been enhanced by adopting the International Society of Urological Pathology (ISUP) 2014 grading classification. This study investigates the effect of training on interobserver variability of PCa grading, using the ISUP Education web e-learning on Gleason grading.MethodsThe ISUP Education Prostate Test B Module was distributed among Dutch pathologists. The module uses images graded by the ISUP consensus panel consisting of 24 expert uropathologists. Participants graded the same 10 images before and after e-learning. We included those who completed the tests before and after training. We evaluated variation in PCa grading in a fully crossed study design, using linearly weighted kappa values for each pathologist, comparing them to other pathologists and to the ISUP consensus panel. We analysed the improvement in median weighted kappas before and after training, using Wilcoxon’s signed rank-test.ResultsWe included 42 pathologists. Inter-rater reliability between pathologists improved from 0.70 before training to 0.74 after training (p=0.01). When compared with the ISUP consensus panel, five pathologists improved significantly, whereas the kappa of one pathologist was significantly lower after training. All pathologists who improved significantly, graded with less than substantial agreement before training.ConclusionsISUP Prostate Test B e-learning reduces variability in PCa grading. E-learning is a cost-effective method for standardisation of pathology.
|
|
| 26. |
|
|
| 27. |
|
|
| 28. |
|
|
| 29. |
- Kartasalo, K, et al.
(författare)
-
Detection of perineural invasion in prostate needle biopsies with deep neural networks
- 2022
-
Ingår i: Virchows Archiv : an international journal of pathology. - : Springer Science and Business Media LLC. - 1432-2307. ; 481:1, s. 73-82
-
Tidskriftsartikel (refereegranskat)abstract
- The presence of perineural invasion (PNI) by carcinoma in prostate biopsies has been shown to be associated with poor prognosis. The assessment and quantification of PNI are, however, labor intensive. To aid pathologists in this task, we developed an artificial intelligence (AI) algorithm based on deep neural networks. We collected, digitized, and pixel-wise annotated the PNI findings in each of the approximately 80,000 biopsy cores from the 7406 men who underwent biopsy in a screening trial between 2012 and 2014. In total, 485 biopsy cores showed PNI. We also digitized more than 10% (n = 8318) of the PNI negative biopsy cores. Digitized biopsies from a random selection of 80% of the men were used to build the AI algorithm, while 20% were used to evaluate its performance. For detecting PNI in prostate biopsy cores, the AI had an estimated area under the receiver operating characteristics curve of 0.98 (95% CI 0.97–0.99) based on 106 PNI positive cores and 1652 PNI negative cores in the independent test set. For a pre-specified operating point, this translates to sensitivity of 0.87 and specificity of 0.97. The corresponding positive and negative predictive values were 0.67 and 0.99, respectively. The concordance of the AI with pathologists, measured by mean pairwise Cohen’s kappa (0.74), was comparable to inter-pathologist concordance (0.68 to 0.75). The proposed algorithm detects PNI in prostate biopsies with acceptable performance. This could aid pathologists by reducing the number of biopsies that need to be assessed for PNI and by highlighting regions of diagnostic interest.
|
|
| 30. |
|
|
| 31. |
|
|
| 32. |
|
|
| 33. |
|
|
| 34. |
|
|
| 35. |
|
|
| 36. |
|
|
| 37. |
|
|
| 38. |
|
|
| 39. |
|
|
| 40. |
|
|
| 41. |
|
|
| 42. |
|
|
| 43. |
|
|
| 44. |
|
|
| 45. |
|
|
| 46. |
|
|
| 47. |
|
|
| 48. |
|
|
| 49. |
|
|
| 50. |
- Strom, Peter, et al.
(författare)
-
Artificial intelligence for diagnosis and grading of prostate cancer in biopsies : a population-based, diagnostic study
- 2020
-
Ingår i: The Lancet Oncology. - : Elsevier. - 1470-2045 .- 1474-5488. ; 21:2, s. 222-232
-
Tidskriftsartikel (refereegranskat)abstract
- BackgroundAn increasing volume of prostate biopsies and a worldwide shortage of urological pathologists puts a strain on pathology departments. Additionally, the high intra-observer and inter-observer variability in grading can result in overtreatment and undertreatment of prostate cancer. To alleviate these problems, we aimed to develop an artificial intelligence (AI) system with clinically acceptable accuracy for prostate cancer detection, localisation, and Gleason grading.MethodsWe digitised 6682 slides from needle core biopsies from 976 randomly selected participants aged 50–69 in the Swedish prospective and population-based STHLM3 diagnostic study done between May 28, 2012, and Dec 30, 2014 (ISRCTN84445406), and another 271 from 93 men from outside the study. The resulting images were used to train deep neural networks for assessment of prostate biopsies. The networks were evaluated by predicting the presence, extent, and Gleason grade of malignant tissue for an independent test dataset comprising 1631 biopsies from 246 men from STHLM3 and an external validation dataset of 330 biopsies from 73 men. We also evaluated grading performance on 87 biopsies individually graded by 23 experienced urological pathologists from the International Society of Urological Pathology. We assessed discriminatory performance by receiver operating characteristics and tumour extent predictions by correlating predicted cancer length against measurements by the reporting pathologist. We quantified the concordance between grades assigned by the AI system and the expert urological pathologists using Cohen's kappa.FindingsThe AI achieved an area under the receiver operating characteristics curve of 0·997 (95% CI 0·994–0·999) for distinguishing between benign (n=910) and malignant (n=721) biopsy cores on the independent test dataset and 0·986 (0·972–0·996) on the external validation dataset (benign n=108, malignant n=222). The correlation between cancer length predicted by the AI and assigned by the reporting pathologist was 0·96 (95% CI 0·95–0·97) for the independent test dataset and 0·87 (0·84–0·90) for the external validation dataset. For assigning Gleason grades, the AI achieved a mean pairwise kappa of 0·62, which was within the range of the corresponding values for the expert pathologists (0·60–0·73).InterpretationAn AI system can be trained to detect and grade cancer in prostate needle biopsy samples at a ranking comparable to that of international experts in prostate pathology. Clinical application could reduce pathology workload by reducing the assessment of benign biopsies and by automating the task of measuring cancer length in positive biopsy cores. An AI system with expert-level grading performance might contribute a second opinion, aid in standardising grading, and provide pathology expertise in parts of the world where it does not exist.
|
|
