-
Automated Gleason Grading of Prostate Biopsies using Deep Learning
The Gleason score is the most important prognostic marker for prostate c...
read it
-
Handling Inter-Annotator Agreement for Automated Skin Lesion Segmentation
In this work, we explore the issue of the inter-annotator agreement for ...
read it
-
Spectral GUI for Automated Tissue and Lesion Segmentation of T1 Weighted Breast MR Images
We present Spectral GUI, a multiplatform breast MR image analysis tool d...
read it
-
A Patient-Centric Dataset of Images and Metadata for Identifying Melanomas Using Clinical Context
Prior skin image datasets have not addressed patient-level information o...
read it
-
Automated soft tissue lesion detection and segmentation in digital mammography using a u-net deep learning network
Computer-aided detection or decision support systems aim to improve brea...
read it
-
Investigating Correlations of Inter-coder Agreement and Machine Annotation Performance for Historical Video Data
Video indexing approaches such as visual concept classification and pers...
read it
-
Automating the assessment of biofouling in images using expert agreement as a gold standard
Biofouling is the accumulation of organisms on surfaces immersed in wate...
read it
Deep Learning-Based Grading of Ductal Carcinoma In Situ in Breast Histopathology Images
Ductal carcinoma in situ (DCIS) is a non-invasive breast cancer that can progress into invasive ductal carcinoma (IDC). Studies suggest DCIS is often overtreated since a considerable part of DCIS lesions may never progress into IDC. Lower grade lesions have a lower progression speed and risk, possibly allowing treatment de-escalation. However, studies show significant inter-observer variation in DCIS grading. Automated image analysis may provide an objective solution to address high subjectivity of DCIS grading by pathologists. In this study, we developed a deep learning-based DCIS grading system. It was developed using the consensus DCIS grade of three expert observers on a dataset of 1186 DCIS lesions from 59 patients. The inter-observer agreement, measured by quadratic weighted Cohen's kappa, was used to evaluate the system and compare its performance to that of expert observers. We present an analysis of the lesion-level and patient-level inter-observer agreement on an independent test set of 1001 lesions from 50 patients. The deep learning system (dl) achieved on average slightly higher inter-observer agreement to the observers (o1, o2 and o3) (κ_o1,dl=0.81, κ_o2,dl=0.53, κ_o3,dl=0.40) than the observers amongst each other (κ_o1,o2=0.58, κ_o1,o3=0.50, κ_o2,o3=0.42) at the lesion-level. At the patient-level, the deep learning system achieved similar agreement to the observers (κ_o1,dl=0.77, κ_o2,dl=0.75, κ_o3,dl=0.70) as the observers amongst each other (κ_o1,o2=0.77, κ_o1,o3=0.75, κ_o2,o3=0.72). In conclusion, we developed a deep learning-based DCIS grading system that achieved a performance similar to expert observers. We believe this is the first automated system that could assist pathologists by providing robust and reproducible second opinions on DCIS grade.
READ FULL TEXT
Comments
There are no comments yet.