Rapid automated diagnosis of primary hepatic tumour by mass spectrometry and artificial intelligence.

BACKGROUND AND AIMS: Complete surgical resection with negative margin is one of the pillars in treatment of liver tumours. However, current techniques for intra-operative assessment of tumour resection margins are time-consuming and empirical. Mass spectrometry (MS) combined with artificial intelligence (AI) is useful for classifying tissues and provides valuable prognostic information. The aim of this study was to develop a MS-based system for rapid and objective liver cancer identification and classification. METHODS: A large dataset derived from 222 patients with hepatocellular carcinoma (HCC, 117 tumours and 105 non-tumours) and 96 patients with mass-forming cholangiocarcinoma (MFCCC, 50 tumours and 46 non-tumours) were analysed by Probe Electrospray Ionization (PESI) MS. AI by means of support vector machine (SVM) and random forest (RF) algorithms was employed. For each classifier, sensitivity, specificity and accuracy were calculated. RESULTS: The overall diagnostic accuracy exceeded 94% in both the AI algorithms. For identification of HCC vs non-tumour tissue, RF was the best, with 98.2% accuracy, 97.4% sensitivity and 99% specificity. For MFCCC vs non-tumour tissue, both algorithms gave 99.0% accuracy, 98% sensitivity and 100% specificity. CONCLUSIONS: The herein reported MS-based system, combined with AI, permits liver cancer identification with high accuracy. Its bench-top size, minimal sample preparation and short working time are the main advantages. From diagnostics to therapeutics, it has the potential to influence the decision-making process in real-time with the ultimate aim of improving cancer patient cure.

Utility of mass spectrometry and artificial intelligence for differentiating primary lung adenocarcinoma and colorectal metastatic pulmonary tumor.

BACKGROUND: Rapid intraoperative diagnosis for unconfirmed pulmonary tumor is extremely important for determining the optimal surgical procedure (lobectomy or sublobar resection). Attempts to diagnose malignant tumors using mass spectrometry (MS) have recently been described. This study evaluated the usefulness of MS and artificial intelligence (AI) for differentiating primary lung adenocarcinoma (PLAC) and colorectal metastatic pulmonary tumor. METHODS: Pulmonary samples from 40 patients who underwent pulmonary resection for PLAC (20 tumors, 20 normal lungs) or pulmonary metastases originating from colorectal metastatic pulmonary tumor (CRMPT) (20 tumors, 20 normal lungs) were collected and analyzed retrospectively by probe electrospray ionization-MS. AI using random forest (RF) algorithms was employed to evaluate the accuracy of each combination. RESULTS: The accuracy of the machine learning algorithm applied using RF to distinguish malignant tumor (PLAC or CRMPT) from normal lung was 100%. The algorithms offered 97.2% accuracy in differentiating PLAC and CRMPT. CONCLUSIONS: MS combined with an AI system demonstrated high accuracy not only for differentiating cancer from normal tissue, but also for differentiating between PLAC and CRMPT with a short working time. This method shows potential for application as a support tool facilitating rapid intraoperative diagnosis to determine the surgical procedure for pulmonary resection.

Continuous-Flow Synthesis of N-Succinimidyl 4-[18F]fluorobenzoate Using a Single Microfluidic Chip.

In the field of positron emission tomography (PET) radiochemistry, compact microreactors provide reliable and reproducible synthesis methods that reduce the use of expensive precursors for radiolabeling and make effective use of the limited space in a hot cell. To develop more compact microreactors for radiosynthesis of 18F-labeled compounds required for the multistep procedure, we attempted radiosynthesis of N-succinimidyl 4-[18F]fluorobenzoate ([18F]SFB) via a three-step procedure using a microreactor. We examined individual steps for [18F]SFB using a batch reactor and microreactor and developed a new continuous-flow synthetic method with a single microfluidic chip to achieve rapid and efficient radiosynthesis of [18F]SFB. In the synthesis of [18F]SFB using this continuous-flow method, the three-step reaction was successfully completed within 6.5 min and the radiochemical yield was 64 ± 2% (n = 5). In addition, it was shown that the quality of [18F]SFB synthesized on this method was equal to that synthesized by conventional methods using a batch reactor in the radiolabeling of bovine serum albumin with [18F]SFB.

Reactivity of electrochemically concentrated anhydrous [18F]fluoride for microfluidic radiosynthesis of 18F-labeled compounds.

In order to demonstrate the usefulness of electrochemically concentrated [(18)F]fluoride the reactivity of the [K(+)/K.222] (18)F(-) complex concentrated in an aprotic solvent (ca. 60µL) was evaluated via nucleophilic (18)F-substitution reactions through radiosynthesis of [(18)F]FDG, [(18)F]FMISO, [(18)F]flumazenil and [(18)F]fluoromethyl bromide. The substitutions were carried out in a microfluidic reaction flow cell and the effects of reaction time, temperature, precursor concentration and reaction solvent on the (18)F-substitution yields were investigated. The (18)F-fluorination yields for the four (18)F-labeled compounds under optimized conditions (98% for protected [(18)F]FDG, 80% for protected [(18)F]FMISO, 20% for [(18)F]flumazenil and 60% for [(18)F]fluoromethyl bromide) were comparable to or higher than those obtained by conventional means. In this study it is clearly demonstrated that electrochemically concentrated [(18)F]fluoride enables microfluidic radiosynthesis by effectively reducing synthesis times and especially by increasing radiochemical yields of products labile at high temperatures.

Electrochemical concentration of no-carrier-added [(18)F]fluoride from [(18)O]water in a disposable microfluidic cell for radiosynthesis of (18)F-labeled radiopharmaceuticals.

The realization of the electrochemical method for microfluidic radiosynthesis is described for concentrating aqueous no-carrier-added [(18)F]fluoride into an aprotic solvent in a disposable microfluidic cell. Flowing aqueous [(18)F]fluoride was introduced into a disposable microfluidic cell (16microL) under an electric potential (10V), followed by anhydrous MeCN. The trapped [(18)F]fluoride was released in MeCN containing Kryptofix 222-KHCO(3) (ca. 60microL) under heat and a reversed potential (-2.5V). An automated module provided the [(18)F]fluoride ready for subsequent microfluidic radiosynthesis in overall radiochemical yields of 60% within 6min.

Amperometric uric acid sensors based on polyelectrolyte multilayer films.

Uricase (UOx) and polyelectrolyte were used for preparation of a permselective multilayer film and enzyme multilayer films on a platinum (Pt) electrode, allowing the detection of uric acid amperometrically. The polyelectrolyte multilayer (PEM) film composed of poly(allylamine) (PAA) and poly(vinyl sulfate) (PVS) were prepared via layer-by-layer assembly on the electrode, functioning as H(2)O(2)-selective film. After deposition of the permselective film (PAA/PVS)(2)PAA, UOx and PAA were deposited via layer-by-layer sequential deposition up to 10 UOx layers to prepare amperometric sensors for uric acid. Current response to uric acid was recorded at +0.6 V vs. Ag/AgCl to detect H(2)O(2) produced from the enzyme reaction. The response current increased with increasing the number of UOx layers. Even in the presence of ascorbic acid, uric acid can be detected over the concentration range 10(-6)-10(-3) M. The response current and deposited amount of UOx were affected by deposition bath pH and the addition of salt. The deposition of PAA/UOx film prepared in 2 mg ml(-1) solution (pH 11) of PAA with NaCl (8 mg ml(-1)) and 0.1 mg ml(-1) solution (pH 8.5) of UOx with borate (100 mM) resulted in an electrode which shows the largest response to uric acid. The response of the sensor to uric acid was decreased by 40% from the original activity after 30 days.