Publications by authors named "Rajmohan Paspulati"

Article Synopsis
  • The study focuses on improving the evaluation of locally advanced rectal cancers by using U-Net deep learning models to automatically segment critical rectal structures from MRI scans, aiming to ease the labor-intensive manual annotation process.
  • Results showed that the region-specific U-Net models achieved high accuracy in segmenting the outer rectal wall and lumen, performing similarly to multiple trained readers, and outperforming a standard multi-class U-Net model by an average of 20%.
  • This advancement in deep learning for MRI analysis can lead to more precise tumor evaluations and enhance the development of image-based tools essential for treating rectal cancers after neoadjuvant therapy.
View Article and Find Full Text PDF

Cervical cancer is the second most encountered cancer in pregnant patients. The 2018 International Federation of Gynecology and Obstetrics (FIGO) staging system for cervical cancer updated the staging of primary cervical carcinoma and disease process, with formal incorporation of imaging as a vital source of information in the management process to improve accuracy. Diagnosis and treatment of the pregnant population is a complex interplay of achieving adequate diagnostic information and optimal treatment while minimizing toxicity and risks to the mother and fetus.

View Article and Find Full Text PDF

Background: Early identification of Crohn's disease (CD) patients at risk for complications could enable targeted surgical referral, but routine magnetic resonance enterography (MRE) has not been definitively correlated with need for surgery. Our objective was to identify computer-extracted image (radiomic) features from MRE associated with risk of surgery in CD and combine them with clinical and radiological assessments to predict time to intervention.

Methods: This was a retrospective single-center pilot study of CD patients who had an MRE within 3 months prior to initiating medical therapy.

View Article and Find Full Text PDF

Primary vaginal cancer is rare, comprising 1% to 2% of gynecologic malignancies and 20% of all malignancies involving the vagina. More frequently, the vagina is involved secondarily by direct invasion from malignancies originating in adjacent organs or by metastases from other pelvic or extrapelvic primary malignancies. Data on the use of imaging in vaginal cancer are sparse.

View Article and Find Full Text PDF

Vulvar cancer is an uncommon gynecologic tumor and one of several human papillomavirus-associated malignancies. Squamous cell carcinoma is the most prevalent histologic subtype of vulvar cancer, accounting for the majority of cases. Imaging plays an important role in managing vulvar cancer.

View Article and Find Full Text PDF

To date, there is little consensus on the role of pelvic imaging in assessing local disease extent during initial staging in patients with endometrial carcinoma, with practices differing widely across centers. However, when pretreatment assessment of local tumor extent is indicated, MRI is the preferred imaging modality. Preoperative imaging of endometrial carcinoma can define the extent of disease and indicate the need for subspecialist referral in the presence of deep myometrial invasion, cervical extension, or suspected lymphadenopathy.

View Article and Find Full Text PDF

(1) : The relatively poor expert restaging accuracy of MRI in rectal cancer after neoadjuvant chemoradiation may be due to the difficulties in visual assessment of residual tumor on post-treatment MRI. In order to capture underlying tissue alterations and morphologic changes in rectal structures occurring due to the treatment, we hypothesized that radiomics texture and shape descriptors of the rectal environment (e.g.

View Article and Find Full Text PDF

Background: Twenty-five percent of rectal adenocarcinoma patients achieve pathologic complete response (pCR) to neoadjuvant chemoradiation and could avoid proctectomy. However, pretreatment clinical or imaging markers are lacking in predicting response to chemoradiation. Radiomic texture features from MRI have recently been associated with therapeutic response in other cancers.

View Article and Find Full Text PDF

Gestational trophoblastic disease (GTD), a rare complication of pregnancy, includes both benign and malignant forms, the latter collectively referred to as gestational trophoblastic neoplasia (GTN). When metastatic, the lungs are the most common site of initial spread. Beta-human chorionic gonadotropin, elaborated to some extent by all forms of GTD, is useful in facilitating disease detection, diagnosis, monitoring treatment response, and follow-up.

View Article and Find Full Text PDF