| 1. |
- Liu, Qianwei, et al.
(författare)
-
Cardiovascular Diseases And Psychiatric Disorders During The Diagnostic Workup Of Suspected Hematological Malignancy
- 2019
-
Ingår i: Clinical Epidemiology. - 1179-1349. ; 11, s. 1025-1034
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Little attention has been given to the risk of cardiovascular and psychiatric comorbidities during the clinical evaluation of a suspected hematological malignancy.Methods: Based on Skåne Healthcare Register, we performed a population-based cohort study of 1,527,449 individuals residing during 2005-2014 in Skåne, Sweden. We calculated the incidence rate ratios (IRRs) of cardiovascular diseases or psychiatric disorders during the diagnostic workup of 5495 patients with hematological malignancy and 18,906 individuals that underwent a bone marrow aspiration or biopsy or lymph node biopsy without receiving a diagnosis of any malignancy ("biopsied individuals"), compared to individuals without such experience (i.e., reference).Results: There was a higher rate of cardiovascular diseases during the diagnostic workup of patients with hematological malignancy (overall IRR, 3.3; 95% CI, 2.9 to 3.8; greatest IRR for embolism and thrombosis, 8.1; 95% CI, 5.2 to 12.8) and biopsied individuals (overall IRR, 4.9; 95% CI, 4.6 to 5.3; greatest IRR for stroke, 37.5; 95% CI, 34.1 to 41.2), compared to reference. Similarly, there was a higher rate of psychiatric disorders during the diagnostic workup of patients with hematological malignancy (IRR, 2.1; 95% CI, 1.5 to 2.8) and biopsied individuals (IRR, 3.1; 95% CI, 2.9 to 3.4). The rate increases were greater around the time of diagnosis or biopsy, compared to thereafter, for both outcomes.Conclusion: There were higher rates of cardiovascular diseases and psychiatric disorders during the diagnostic workup of a suspected hematological malignancy, regardless of the final diagnosis.
|
|
| 3. |
- Tomic, Hanna, et al.
(författare)
-
Using simulated breast lesions based on Perlin noise for evaluation of lesion segmentation
- 2024
-
Ingår i: Medical Imaging 2024 : Physics of Medical Imaging - Physics of Medical Imaging. - : SPIE-Intl Soc Optical Eng. - 1605-7422. - 9781510671546 ; 12925
-
Konferensbidrag (refereegranskat)abstract
- Segmentation of diagnostic radiography images using deep learning is progressively expanding, which sets demands on the accessibility, availability, and accuracy of the software tools used. This study aimed at evaluating the performance of a segmentation model for digital breast tomosynthesis (DBT), with the use of computer-simulated breast anatomy. We have simulated breast anatomy and soft tissue breast lesions, by utilizing a model approach based on the Perlin noise algorithm. The obtained breast phantoms were projected and reconstructed into DBT slices using a publicly available open-source reconstruction method. Each lesion was then segmented using two approaches: 1. the Segment Anything Model (SAM), a publicly available AI-based method for image segmentation and 2. manually by three human observers. The lesion area in each slice was compared to the ground truth area, derived from the binary mask of the lesion model. We found similar performance between SAM and manual segmentation. Both SAM and the observers performed comparably in the central slice (mean absolute relative error compared to the ground truth and standard deviation SAM: 4 ± 3 %, observers: 3 ± 3 %). Similarly, both SAM and the observers overestimated the lesion area in the peripheral reconstructed slices (mean absolute relative error and standard deviation SAM: 277 ± 190 %, observers: 295 ± 182 %). We showed that 3D voxel phantoms can be used for evaluating different segmentation methods. In preliminary comparison, tumor segmentation in simulated DBT images using SAM open-source method showed a similar performance as manual tumor segmentation.
|
|
