| 1. |
- Kindler, Csaba, et al.
(author)
-
A Deep Neural Network-Based Decision Support Tool for the Detection of Lymph Node Metastases in Colorectal Cancer Specimens
- 2023
-
In: Modern Pathology. - : Elsevier. - 0893-3952 .- 1530-0285. ; 36:2
-
Journal article (peer-reviewed)abstract
- The identification of lymph node metastases in colorectal cancer (CRC) specimens is crucial for the planning of postoperative treatment and can be a time-consuming task for pathologists. In this study, we developed a deep neural network (DNN) algorithm for the detection of metastatic CRC in digitized histologic sections of lymph nodes and evaluated its performance as a diagnostic support tool. First, the DNN algorithm was trained using pixel-level annotations of cancerous areas on 758 whole slide images (360 with cancerous areas). The algorithm's performance was evaluated on 74 whole slide images (43 with cancerous areas). Second, the algorithm was evaluated as a decision support tool on 288 whole slide images covering 1517 lymph node sections, randomized in 16 batches. Two senior pathologists (C.K. and C.O.) assessed each batch with and without the help of the algorithm in a 2 x 2 crossover design, with a washout period of 1 month in between. The time needed for the evaluation of each node section was recorded. The DNN algorithm achieved a median pixel-level accuracy of 0.952 on slides with cancerous areas and 0.996 on slides with benign samples. N+ disease (metastases, micrometastases, or tumor deposits) was present in 103 of the 1517 sections. The algorithm highlighted cancerous areas in 102 of these sections, with a sensitivity of 0.990. Assisted by the algorithm, the median time needed for evaluation was significantly shortened for both pathologists (median time for pathologist 1, 26 vs 14 seconds; P < .001; 95% CI, 11.0-12.0; median time for pathologist 2, 25 vs 23 seconds; P < .001; 95% CI, 2.0-4.0). Our DNN showed high accuracy for detecting metastatic CRC in digitized histologic sections of lymph nodes. This decision support tool has the potential to improve the diagnostic workflow by shortening the time needed for the evaluation of lymph nodes in CRC specimens without impairing diagnostic accuracy.
|
|
| 2. |
- Tiselius, Catarina, et al.
(author)
-
Importance of Arterial Vessel Length for Metastatic Lymph Node Retrieval and Survival in Standardized Left- and Right-Sided Colon Cancer Surgery
- 2023
-
In: Journal of Gastrointestinal Cancer. - : Springer Nature. - 1941-6628 .- 1941-6636. ; 54:3, s. 809-819
-
Journal article (peer-reviewed)abstract
- Background We investigated the localization of lymph node metastases, and the role of arterial vessel and specimen lengths in left- and right-sided colon cancer surgery, for survival. Methods This was a prospective cross-sectional population-based study of specimens from patients who underwent standardized surgical resection for colon cancer in 2012-2015. The mesocolon of the specimens was divided into four sections for pathological analysis of lymph nodes. Multiple linear regression analysis was used to explore the relationship between lymph node counts and patient- and surgery-related factors. For survival analysis, a multivariable Cox regression method was used. Results A total of 317 patients (160 females) were included. Median (range) age was 74 (30-95) years. Median number of lymph node retrieval was 32 (8-198) and was associated with increased specimen length but not to arterial vessel length. One hundred and thirty-three (42%) patients had lymph node metastases. All patients had these located < 5 cm from the tumour. Ten, two, and three specimens had lymph node metastases around the central and peripheral ligation of the ileocolic artery and at the central ligation of the inferior mesenteric artery, respectively. The tumour stages in these specimens were T3-4N2M0-1. No statistically significant survival benefit was associated with longer arterial vessel length (p = 0.429). Conclusions Neither retrieval of lymph nodes nor statistically significant survival was affected by vessel length in standardized left- and right-sided colon cancer surgery.
|
|
