Deep Learning Nomogram for the Identification of Deep Stromal Invasion in Patients With Early-Stage Cervical Adenocarcinoma and Adenosquamous Carcinoma: A Multicenter Study.

BACKGROUND: Deep stromal invasion (DSI) is one of the predominant risk factors that determined the types of radical hysterectomy (RH). Thus, the accurate assessment of DSI in cervical adenocarcinoma (AC)/adenosquamous carcinoma (ASC) can facilitate optimal therapy decision. PURPOSE: To develop a nomogram to identify DSI in cervical AC/ASC. STUDY TYPE: Retrospective. POPULATION: Six hundred and fifty patients (mean age of 48.2 years) were collected from center 1 (primary cohort, 536), centers 2 and 3 (external validation cohorts 1 and 2, 62 and 52). FIELD STRENGTH/SEQUENCE: 5-T, T2-weighted imaging (T2WI, SE/FSE), diffusion-weighted imaging (DWI, EPI), and contrast-enhanced T1-weighted imaging (CE-T1WI, VIBE/LAVA). ASSESSMENT: The DSI was defined as the outer 1/3 stromal invasion on pathology. The region of interest (ROI) contained the tumor and 3 mm peritumoral area. The ROIs of T2WI, DWI, and CE-T1WI were separately imported into Resnet18 to calculate the DL scores (TDS, DDS, and CDS). The clinical characteristics were retrieved from medical records or MRI data assessment. The clinical model and nomogram were constructed by integrating clinical independent risk factors only and further combining DL scores based on primary cohort and were validated in two external validation cohorts. STATISTICAL TESTS: Student's t-test, Mann-Whitney U test, or Chi-squared test were used to compare differences in continuous or categorical variables between DSI-positive and DSI-negative groups. DeLong test was used to compare AU-ROC values of DL scores, clinical model, and nomogram. RESULTS: The nomogram integrating menopause, disruption of cervical stromal ring (DCSRMR), DDS, and TDS achieved AU-ROCs of 0.933, 0.807, and 0.817 in evaluating DSI in primary and external validation cohorts. The nomogram had superior diagnostic ability to clinical model and DL scores in primary cohort (all P < 0.0125 [0.05/4]) and CDS (P = 0.009) in external validation cohort 2. DATA CONCLUSION: The nomogram achieved good performance for evaluating DSI in cervical AC/ASC. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY: Stage 2.

Intratumoral and peritumoral MRI radiomics nomogram for predicting parametrial invasion in patients with early-stage cervical adenocarcinoma and adenosquamous carcinoma.

OBJECTIVE: To develop a comprehensive nomogram based on MRI intra- and peritumoral radiomics signatures and independent risk factors for predicting parametrial invasion (PMI) in patients with early-stage cervical adenocarcinoma (AC) and adenosquamous carcinoma (ASC). METHODS: A total of 460 patients with IB to IIB cervical AC and ASC who underwent preoperative MRI examination and radical trachelectomy/hysterectomy were retrospectively enrolled and divided into primary, internal validation, and external validation cohorts. The original (Ori) and wavelet (Wav)-transform features were extracted from the volumetric region of interest of the tumour (ROI-T) and 3mm- and 5mm-peritumoral rings (ROI-3 and ROI-5), respectively. Then the Ori and Ori-Wav feature-based radiomics signatures from the tumour (RST) and 3 mm- and 5 mm-peritumoral regions (RS3 and RS5) were independently built and their diagnostic performances were compared to select the optimal ones. Finally, the nomogram was developed by integrating optimal intra- and peritumoral signatures and clinical independent risk factors based on multivariable logistic regression analysis. RESULTS: FIGO stage, disruption of the cervical stromal ring on MRI (DCSRMR), parametrial invasion on MRI (PMIMR), and serum CA-125 were identified as independent risk factors. The nomogram constructed by integrating independent risk factors, Ori-Wav feature-based RST, and RS5 yielded AUCs of 0.874 (0.810-0.922), 0.885 (0.834-0.924), and 0.966 (0.887-0.995) for predicting PMI in the primary, internal and external validation cohorts, respectively. Furthermore, the nomogram was superior to radiomics signatures and clinical model for predicting PMI in three cohorts. CONCLUSION: The nomogram can preoperatively, accurately, and noninvasively predict PMI in patients with early-stage cervical AC and ASC. CLINICAL RELEVANCE STATEMENT: The nomogram can preoperatively, accurately, and noninvasively predict PMI and facilitate precise treatment decisions regarding chemoradiotherapy or radical hysterectomy in patients with early-stage cervical AC and ASC. KEY POINTS: The accurate preoperative prediction of PMI in early-stage cervical AC and ASC can facilitate precise treatment decisions regarding chemoradiotherapy or radical hysterectomy. The nomogram integrating independent risk factors, Ori-Wav feature-based RST, and RS5 can preoperatively, accurately, and noninvasively predict PMI in early-stage cervical AC and ASC. The nomogram was superior to radiomics signatures and clinical model for predicting PMI in early-stage cervical AC and ASC.

Primary Adenosquamous Carcinoma of the Prostate With Multiple Heterogenic Metastases Demonstrated on 68 Ga-PSMA and 18 F-FDG PET/CT Imaging.

ABSTRACT: A 54-year-old man presented with a 2-month history of urination disturbances. Serum prostate-specific antigen level was 4.96 ng/mL, and a possibility of benign prostate hyperplasia was raised by outside medical CT. Histopathology revealed adenosquamous carcinoma. Staging workup showed large areas of high PSMA uptake and focal intense hypermetabolism in the prostate, multiple lymphatics, bone, and pulmonary heterogenic metastases on 68 Ga-PSMA and 18 F-FDG PET/CT imaging.

Adenosquamous carcinoma of the liver: The challenge of diagnosis.

Adenosquamous carcinoma of the liver is extremely rare. We report a case of adenosquamous carcinoma in the intrahepatic bile duct of a 56-year-old woman who complained of persistent abdominal pain, shivering and hyperthermia. Computed tomography demonstrated a solid-cystic neoplasm in segment 5/6/8 of the liver with a gradual enhancement pattern in the solid area. However, postoperative pathological examination showed adenosquamous carcinoma of intrahepatic bile duct.

Adenosquamous carcinoma lung radiologically mimicking pneumonia: A potentially disastrous diagnostic challenge in an unusual malignancy.

Lung cancer is among the most frequently diagnosed cancers and the world's leading cause of cancer-related death. Radiology remains the mainstay for timely diagnosis; however, atypical radiologic patterns are known, and these may be misdiagnosed as infectious or inflammatory pathology, particularly in the absence of smoking history. We report herein an account of an older male nonsmoker who presented radiologically with bilateral diffuse pulmonary infiltrates, simulating pneumonia, but was eventually diagnosed with adenosquamous lung carcinoma. The delay in diagnosis and subsequent unfortunate rapid deterioration of our patient serves as a reminder for clinicians to consider lung cancer in patients with clinical/radiologic findings suggestive of pneumonia, especially in nonsmokers or cases refractory to antibiotic therapy.

Adenosquamous carcinoma of the gallbladder: a rare entity and dilemmas in its management.

Gallbladder carcinomas are the most common form of biliary tract malignancies with adenocarcinomas, by far the most common variant while adenosquamous (adenosquamous carcinoma of the gallbladder) or pure squamous cell carcinomas representing only 2%-10% of all gallbladder carcinomas. Despite being a minority, these tumours demonstrate aggressive behaviour resulting in delayed presentations with widespread local invasion. We report a case involving a woman in her 50s who was diagnosed on imaging with a suspected gallbladder malignancy in the community. She proceeded to have a laparoscopic extended cholecystectomy with a cuff of segment 4b and 5 liver resection and cystic node sampling revealing a T3N1 lesion which on further recommendation by the multidisciplinary team proceeded to have an open portal lymphadenectomy yielding another positive lymph node. This case report highlights the dilemmas encountered in the management of this rare histological subtype in the absence of well-defined treatment algorithm and evolving guidelines.

Fully automated magnetic resonance imaging-based radiomics analysis for differentiating pancreatic adenosquamous carcinoma from pancreatic ductal adenocarcinoma.

PURPOSE: To develop and validate an automated magnetic resonance imaging (MRI)-based model to preoperatively differentiate pancreatic adenosquamous carcinoma (PASC) from pancreatic ductal adenocarcinoma (PDAC). METHODS: This retrospective study included patients with surgically resected, histopathologically confirmed PASC or PDAC who underwent MRI between January 2011 and December 2020. According to time of treatment, they were divided into training and validation sets. Automated deep-learning-based artificial intelligence was used for pancreatic tumor segmentation. Linear discriminant analysis was performed with conventional MRI and radiomic features to develop clinical, radiomics, and mixed models in the training set. The models' performances were determined from their discrimination and clinical utility. Kaplan-Meier and log-rank tests were used for survival analysis. RESULTS: Overall, 389 and 123 patients with PDAC (age, 61.37 ± 9.47 years; 251 men) and PASC (age, 61.99 ± 9.82 years; 78 men) were included, respectively; they were split into the training (n = 358) and validation (n = 154) sets. The mixed model showed good performance in the training and validation sets (area under the curve: 0.94 and 0.96, respectively). The sensitivity, specificity, and accuracy were 76.74%, 93.38%, and 89.39% for the training set, respectively, and 67.57%, 97.44%, and 90.26% for the validation set, respectively. The mixed model outperformed the clinical (p = 0.001) and radiomics (p = 0.04) models in the validation set. Log-rank test revealed significantly longer survival in the predicted PDAC group than in the predicted PASC group (p = 0.003), according to the mixed model. CONCLUSION: Our mixed model, which combined MRI and radiomic features, can be used to differentiate PASC from PDAC.

Adenosquamous carcinoma of the pancreas: two case reports and review of the literature.

BACKGROUND: Among the total reported cases of pancreatic duct adenocarcinomas, around 1-2.9% are adenosquamous carcinomas of the pancreas. Due to limited data, preoperative diagnosis is a great challenge for physicians, and it is usually set post-operational, based on the pathologist report. We operated on two cases of adenosquamous carcinoma of the pancreas, which we present alongside the operation and treatment planning. CASE REPORT: A 69-year-old Caucasian female and a 63-year-old Caucasian male presented themselves with jaundice in our department. The abdomen computed tomography and magnetic resonance imaging scans revealed lesions of the pancreas. A pancreas-duodenumectomy was performed in both patients, and the post-operational histology analysis revealed adenosquamous carcinoma of the pancreas head. The patients were discharged in good condition and received further chemotherapy treatment after surgery. CONCLUSIONS: Two case reports of adenosquamous carcinoma of the pancreas are described here, which both underwent surgery resection. The limited available literature on this topic substantially limits the knowledge and guidance on treatment. A summarization of the available literature is attempted, alongside a description of possible fields of future research.

Application of Unenhanced Computed Tomography Texture Analysis to Differentiate Pancreatic Adenosquamous Carcinoma from Pancreatic Ductal Adenocarcinoma.

OBJECTIVE: The objective of this study was to investigate the application of unenhanced computed tomography (CT) texture analysis in differentiating pancreatic adenosquamous carcinoma (PASC) from pancreatic ductal adenocarcinoma (PDAC). METHODS: Preoperative CT images of 112 patients (31 with PASC, 81 with PDAC) were retrospectively reviewed. A total of 396 texture parameters were extracted from AnalysisKit software for further texture analysis. Texture features were selected for the differentiation of PASC and PDAC by the Mann-Whitney U test, univariate logistic regression analysis, and the minimum redundancy maximum relevance algorithm. Furthermore, receiver operating characteristic (ROC) curve analysis was performed to evaluate the diagnostic performance of the texture feature-based model by the random forest (RF) method. Finally, the robustness and reproducibility of the predictive model were assessed by the 10-times leave-group-out cross-validation (LGOCV) method. RESULTS: In the present study, 10 texture features to differentiate PASC from PDAC were eventually retained for RF model construction after feature selection. The predictive model had a good classification performance in differentiating PASC from PDAC, with the following characteristics: sensitivity, 95.7%; specificity, 92.5%; accuracy, 94.3%; positive predictive value (PPV), 94.3%; negative predictive value (NPV), 94.3%; and area under the ROC curve (AUC), 0.98. Moreover, the predictive model was proved to be robust and reproducible using the 10-times LGOCV algorithm (sensitivity, 90.0%; specificity, 71.3%; accuracy, 76.8%; PPV, 59.0%; NPV, 95.2%; and AUC, 0.80). CONCLUSION: The unenhanced CT texture analysis has great potential for differentiating PASC from PDAC.

De-differentiated metastatic adenosquamous carcinoma arising from germ cell tumor in the brain and spine.

Intracranial germ cell tumors have an estimated incidence of 0.4-3.4% in the Western Hemisphere. Patients can present with a variety of differing clinical signs and symptoms including headache, nausea/vomiting, hydrocephalus, obtundation, pyramidal tract signs, ataxia, and hypothalamic/pituitary dysfunction. Rarely germ cell tumors can transform into alternative malignancy. In these cases, treatment options may be difficult. Metastasis to the brain is not uncommon in germ cell tumors and is frequently reported within the pineal region; however, they are less common intraventricularly, within the posterior fossa and have never been reported after malignant transformation. Herein, we present the first reported case of a metastatic adenosquamous carcinoma transformed from a yolk sac tumor with diffuse cerebral metastasis in atypical locations of the brain including intraventricular and posterior fossa. A 53-year-old right-handed Caucasian female was transferred from an outside hospital for a chief complaint of altered mental status with CT head showing right side intraventricular mass and cerebellar hemorrhage. MRI of the brain found multifocal contrast-enhancing lesions of the right lateral ventricle, right cerebellum, right frontal lobe, diffuse lumbar dural enhancement, and an intramedullary lesion at the cervico-medullary junction of the brainstem. The right lateral ventricular lesion and right cerebellar lesions were resected. Pathology findings support a diagnosis of adenosquamous carcinoma, and the morphologic and immunophenotypic features suggest development as a somatic malignancy in a germ cell neoplasm with features of a yolk sac tumor. Germ cell tumors are typically included within the differential of pineal region masses; however, other locations such as intraventricular and posterior fossa are rarely seen. Even rarer are cases with malignant transformation to an alternative lesion for which treatment options are exceptionally scarce. Neurosurgeons and oncologists alike should be aware of this rare possible lesion to add to a broad differential diagnosis.

Whole-tumor histogram analysis of apparent diffusion coefficient for differentiating adenosquamous carcinoma and adenocarcinoma from squamous cell carcinoma in patients with cervical cancer.

BACKGROUND: Differentiating adenosquamous carcinoma (ASC) and adenocarcinoma (AC) from squamous cell carcinoma (SCC) precisely is crucial for treatment strategy and prognosis prediction in patients with cervical cancer (CC). PURPOSE: To differentiate ASC and AC from SCC in patients with CC using the apparent diffusion coefficient (ADC) histogram analysis. MATERIAL AND METHODS: A total of 118 patients with histologically diagnosed ASC, AC, and SCC were included. The ADC histogram parameters were extracted from ADC maps. Receiver operating characteristic analysis was performed to evaluate the diagnostic performance of each ADC histogram parameter in differentiating the subtypes of CC. The predictors for histologic subtypes were further selected using univariate and multivariate logistic regression analyses. RESULTS: The ADCmean, ADCmax, ADCP10, ADCP25, ADCP75, ADCP90, ADCmedian, and ADCmode of the ASC were significantly lower than those of the AC; and ADCkurtosis and ADCskewness of the ASC were lower than those of the SCC. The ADCmean, ADCmax, ADCP10, ADCP25, ADCP75, ADCP90, ADCmedian, and ADCmode of AC were significantly higher than those of the SCC. The ADCP10 and ADCP10 + diameter yielded the AUCs of 0.753 and 0.778 in differentiating ASC from AC. The ADCmedian and ADCmedian + diameter yielded the AUCs of 0.807 and 0.838 in differentiating AC from SCC. The ADCskewness yielded the AUC of 0.713 in differentiating ASC from SCC. CONCLUSION: The ADCP10 and ADCP10 + diameter, ADCmedian, and ADCmedian + diameter performed well in differentiating ASC from AC and AC from SCC, respectively. However, ADCskewness exhibited a limited ability in differentiating ASC from SCC.

Ultrasonographic diagnosis in rare primary cervical cancer.

INTRODUCTION: Although ultrasonography has been reported to have similar diagnostic accuracy to magnetic resonance imaging, it is not a standard imaging modality for cervical cancer. We aimed to summarize the ultrasonographic features of rare primary cervical cancer. METHODS: This was a retrospective study of patients with cervical cancer who were diagnosed between June 2014 and October 2019. They were divided into common-type cervical cancer (ie, cervical squamous cell carcinoma) and rare-type cervical cancer groups including adenocarcinoma, adenosquamous carcinoma, and small cell carcinoma. All patients were staged according to the tumor, nodes, and metastases criteria. RESULTS: Of the 64 patients, the diagnosis was suspected on ultrasonography in 61 (95.3%) patients and missed on ultrasonography in three patients. The tumor size was smaller in the rare-type cervical cancer group (p<0.05). Hypoechoic lesions in common-type cervical cancer and isoechoic lesions accounted for 74.4% (32/43) and 61.9% (13/21) of patients in the rare-type cervical cancer group, respectively (p<0.001). Meanwhile, 67.4% (29/43) of tumors in common-type cervical cancer were exophytic, while 66.7% (14/21) in rare-type cervical cancer were endophytic (p=0.01). Color Doppler blood signals, as compared with normal cervical tissue, were found in all patients. There was good consistency between ultrasonographic and pathologic diagnosis of rare-type cervical cancer (weighted kappa=0.87). CONCLUSIONS: Most patients with rare-type cervical cancer present with isoechoic lesions. The coincidence rate between ultrasonographic and pathologic diagnosis of rare-type cervical cancer is 87%.

Primary Adenosquamous Carcinoma of the Liver on FDG PET/CT.

ABSTRACT: Primary adenosquamous carcinoma (ASC) of the liver is a rare subtype of intrahepatic cholangiocarcinoma. Hepatic ASC consists of both adenocarcinoma and squamous cell carcinoma components. Because hepatic ASC is extremely rare, only a few cases describing the imaging findings of hepatic ASC were reported before. Herein, we present FDG PET/CT findings of hepatic ASC in a 78-year-old woman who was admitted to hospital with a 4-week history of right upper quadrant pain.

The 5-year overall survival of cervical cancer in stage IIIC-r was little different to stage I and II: a retrospective analysis from a single center.

BACKGROUND: The 2018 International Federation of Gynecology and Obstetrics (FIGO) staging guideline for cervical cancer includes stage IIIC recognized by preoperative radiology (IIIC-r) to state there are lymph nodes metastases (LNM) identified by imaging tools. We aim to explore the reasonability and limitations of stage IIIC-r and try to explore the potential reasons. METHODS: Electronic medical records were used to identify patients with cervical cancer. According to the new staging guidelines, patients were reclassified and assigned into five cohorts: stage I, stage II, stage IIIC-r, LNM confirmed by pathology (IIIC-p) and LNM detected by radiology and confirmed by pathology (IIIC r + p). Five-year overall survivals were estimated for each cohort. The diagnosis accuracy of computed tomography (CT), magnetic resonance imaging (MRI) and diameter of detected lymph nodes were also evaluated. RESULTS: A total of 619 patients were identified. The mean follow-up months were 65 months (95% CI 64.43-65.77) for all patients. By comparison, the 5-year overall survival rates were not statistically different (p = 0.21) among stage IIIC-r, stage I and stage II. While, the rates were both statistical different (p<0.001) among stage IIIC-p, IIIC r + p and stage I and stage II. The sensitivities of CT and MRI in detecting LNM preoperatively were 51.2 and 48.8%. The mean maximum diameter of pelvic lymph nodes detected by CT cohort was 1.2 cm in IIIC-r cohort, and was 1.3 cm in IIIC r + p cohort. While, the mean maximum diameter of pelvic lymph nodes detected by MRI was 1.2 cm in IIIC-r cohort, and was 1.48 cm in IIIC r + p cohort. When the diagnosis efficacy of the diameter of pelvic lymph nodes in detecting LNM were evaluated, the area under the receiver operating characteristic curve (ROC curve) was 0.58 (p = 0.05). CONCLUSIONS: It seems that the FIGO 2018 staging guideline for cervical cancer is likely to has certain limitations for the classification of those with LNM. CT or MRI, however, has limitations on detecting LNM. It would be better to use more accurate imaging tools to identify LNM in the clinical practices.

Use of ring-enhancement and focal necrosis to differentiate pancreatic adenosquamous carcinoma from pancreatic ductal adenocarcinoma on CT and MRI.

PURPOSE: To assess the ability of the ring-enhancing sign and focal necrosis to diagnose adenosquamous carcinoma (ASqC), a variant of pancreatic ductal adenocarcinoma (PDAC), on MRI and CT. METHODS: The following features of ASqC and conventional PDAC were evaluated on CT and MRI: tumor size, location, margins, borders (non-exophytic, exophytic), and T1 signal intensity. Two readers, blinded to histopathology results, rated their confidence in detecting ring-enhancement and focal necrosis (FN) on a 5-point Likert scale on both MRI and CT. Inter-reader agreement was assessed with Cohen's kappa (k). RESULTS: A total of 24 patients were included: eight patients with treatment naïve and histologically proven ASqC (six women, mean age: 63, range: 40-75) and 16 patients with PDAC (eight women, mean age: 67, range: 47-83). Statistically significant differences between ASqC and PDAC were seen in tumor size, location, presence of FN, and ring enhancement (p = 0.01-0.037). The readers were more confident in depicting the key differentiating feature ring-enhancement in ASqC on MRI compared to CT (confidence 1.71 ± 0.49 vs. 0.88 ± 0.35, p = 0.017) with moderate inter-reader agreement (k = 0.46 and 0.5, respectively). FN showed substantial inter-reader agreement on MR and moderate agreement on CT (k = 0.67 and 0.5, respectively). CONCLUSIONS: Compared to CT, MRI depicts ring-enhancement in ASqC with greater reader confidence and FN in ASqC with higher inter-reader agreement. The concurrent presence of these two imaging features should raise high suspicion for ASqC.

[The Postoperative Recurrence of Adenosquamous Cell Carcinoma of the Lung as a Polypoid Mass in the Tracheal Lumen;Report of a Case].

The case is 77 years old, female. She was referred to a local doctor with a chief complaint of cough and wheezing and was treated as asthma. However, symptoms did not improve and she was referred to our hospital. She had a history of right upper lobectomy for lung cancer about 2 years before, with the pathological diagnosis of adenosquamous cell carcinoma, pT1aN0M0, stage I A. Chest computed tomography (CT) scan showed a pedunculated polypoid mass almost occupying the lumen in the trachea immediately above the tracheal bifurcation, and the emergency bronchoscopic resection using a high-frequency snare under general anesthesia was performed. Postoperatively, 50 Gray of radiotherapy was added.

The Role of Morphologic and Functional Imaging in Pretreatment Assessment.

Anterior skull base (ASB) tumors can be classified into three groups according to their site of origin: (1) sinonasal neoplasms involving or extending through the anterior cranial base; (2) neoplasms which arise from the bony framework of the base itself; (3) neoplasms originating from adjacent intracranial structures. With few exceptions, most of these tumors have a non-specific appearance on CT and MRI, which limits the role of imaging in terms of characterization. However, treatment planning (transnasal endoscopic surgery in particular) mostly depends upon the tumor map, exploiting the potential of modern cross-sectional imaging. As a result, the radiologist who has to evaluate a neoplasm involving the ASB needs to be fully aware of all the technical solutions available and the specific strengths/weaknesses of the different imaging techniques. Knowledge of radiological anatomy (and its variants) is also essential, which includes the ability to translate the CT appearance of structures into the equivalent MR signal (and vice versa). These main prerequisites have to be combined with up-to-date knowledge of treatment options and surgical procedures in order to be able to create a reporting checklist covering all the aspects that are essential for clinical decision making.