=[PresentationsandPublications Back to Presentations and Publications Main Page]=

Final presentation: [[File(pathInformatics2018gallas.pdf)]]

Abstract below and attached: [[File(pathInformatics2018abstractGallas.pdf)]]

Related wikii pages:
 * '''Study on multi-head microscope at MSKCC, June 2017'''
    * [StudyFDAMSKCCmaterials Description and study materials]
 * '''Study on multi-head microscope at MSKCC, November 2017'''
    * [StudyFDAMSKCC14headMicroscope Description and study materials]

= '''A Reader Study on a 14-head Microscope''' =
 * 8:15, Wednesday, 23 May 2018
 * Kings Garden 1
 * Wyndham Hotel, Pittsburgh, PA

==== Authors ====
 * Brandon D. Gallas (1)
 * Jamal Benhamida (2)
 * Qi Gong (1)
 * Matthew G. Hanna (2)
 * Partha P. Mitra (3)
 * S. Joseph Sirintrapun (2)
 * Kazuhiro Tabata (2)
 * Yukako Yagi (2)
(1) FDA/CDRH/OSEL/DIDSR, Silver Spring, MD, US
(2) Memorial Sloan Kettering Cancer Center, Pathology Informatics, New York, NY, US
(3) Cold Spring Harbor Laboratory, Cold Spring Harbor, Neuroscience, NY, US

==== Abstract ====
'''Content'''
In this work, we conducted two feature studies on detecting mitotic figures (MFs) with whole slide images (WSI) and a microscope.
'''Technology'''
Supervised image analysis algorithms are only as good as the ground-truth on which they are trained and tested. The most practical ground-truth is a pathologist’s assessment with WSI. These are limited as the pathologist is unable to focus on nearby planes of a section (as can be done on a microscope). Another limitation arises from inter-pathologist variability. To overcome these limitations, we propose collecting ground truth from multiple pathologists using a microscope.
'''Design'''
We used a custom hardware and software evaluation environment for digital and analog pathology that allows us to automatically present the same regions of interest (ROIs) to a pathologist on a microscope or WSI. In Study 1 we collected MF counts and locations in 40 ROIs from 4 H&E slides of canine oral melanoma (five pathologists, institutional guidelines regarding animal experimentation were followed). The ROIs were 200 um x 200 um (800 x 800 pixels at 0.25 um/pixel; Aperio AT2). Study 2 was conducted on a 14-head microscope (four original + six new pathologists, working independently). We collected MF counts and locations on the same 40 ROIs. In Study 2 we also asked the pathologists to quantify their confidence that a candidate was an MF.
'''Results'''
In Study 1, the pathologists identified 94 “candidate” mitotic figures, and they identified more with the microscope than with the WSI (See Table 1). We call them candidate MFs because only 18 of 94 were unanimously identified. In Study 2, the pathologists identified 170 candidates. More pathologists lead to more candidates. Lastly, we did not find noteworthy differences in the between-reader variability in count differences across the modalities studied (Table 1). More results will be presnted at the conference.
'''Conclusion'''
Detecting and quantifying mitoses is an important pathology task when evaluating tumors of various subtypes; it is also challenging and burdensome to pathologists, subject to significant pathologist variability. Future studies are underway, leveraging the results of these two studies, to train or test an automated mitosis detection algorithm.

'''Table 1: Preliminary Results'''

|| desc                                            || Average Counts    || Std of Average Counts    || Std of Between-Reader Paired Count Differences ||
|| Study 1: Digital                            || 1.22    || 0.23    || 1.29 ||
|| Study 1: Microscope	              || 1.48    || 0.27    || 1.12 ||
|| Study 2: Multi-Head Microscope  || 1.54    || 0.25    || 1.07 ||
|| Study 1: Microscope - Digital       || 0.26    || 0.12    || 1.20 ||